In this paper we propose a novel nonparametric approach
for object recognition and scene parsing using dense
scene alignment. Given an input image, we retrieve its best
matches ...
Depth-map merging approaches have become more and
more popular in multi-view stereo (MVS) because of their
flexibility and superior performance. The quality of depth
map used fo...
Yebin Liu (Tsinghua University), Xun Cao (Tsinghu...
A method is presented to recover 3D scene structure and camera motion from multiple images without the need for correspondence information. The problem is framed as finding the ma...
Frank Dellaert, Steven M. Seitz, Charles E. Thorpe...
Shape symmetry is an important cue for image understanding. In the absence of more detailed prior shape information, segmentation can be significantly facilitated by symmetry. How...
This paper presents a novel spatio-temporal Markov random field (MRF) for video denoising. Two main issues are addressed in this paper, namely, the estimation of noise model and t...